© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28315
    Prev
    Next
    INDEX
    Explanations

    how would I know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ued
    -0.11
     Brand
    -0.10
    jour
    -0.10
     Vaughan
    -0.09
     Dah
    -0.09
     Jur
    -0.09
     Doesn
    -0.09
    atas
    -0.09
     Tick
    -0.09
    jas
    -0.09
    POSITIVE LOGITS
     know
    0.14
     unless
    0.12
     knows
    0.12
    çŁ¥
    0.11
     ever
    0.11
    Know
    0.11
     Know
    0.11
    know
    0.10
    Unless
    0.10
     EVER
    0.10
    Activations Density 0.055%

    No Known Activations